Object's details: Accuracy evaluation of convolutional neural network classification algorithms for building identification in rural and urban areas from very-high-resolution satellite imagery in Jambi, Indonesia

Provider:Akademicka Platforma Czasopism

Description

Title:
Accuracy evaluation of convolutional neural network classification algorithms for building identification in rural and urban areas from very-high-resolution satellite imagery in Jambi, Indonesia
Creator:
Nugroho, Daniel;
Dimyati, Muhammad;
Laswanto
Description:
Accurate land cover data are essential to a reliable decision-making process; therefore, researchers have turned to novel land cover classification algorithms employing machine learning on high-resolution satellite imagery to improve classification accuracy. The experiment presented in this paper aims to assess the accuracy performance of three patch-based, convolutional neural network architectures (LeNet, VGGNet, and XCeption) in classifying building footprints in rural and urban areas from satellite imagery data, with conventional, pixel-based classification algorithms as a benchmark. The experiment concluded that the CNN classification algorithms consistently outperformed pixel-based algorithms in the accuracy of the resulting building-footprint classification raster. It was also demonstrated that larger image patch size does not always improve classification accuracy in all CNN architectures. This study also revealed that the XCeption architecture performed best among the three CNN architectures assessed, with a 72-pixel patch size having the best accuracy.
Object availability:
free access
Rights:
Prawa autorskie (c) 2022 Daniel Nugroho, Muhammad Dimyati, Laswanto;
https://creativecommons.org/licenses/by-nd/4.0
Date:
2022.12.09
Type:
info:eu-repo/semantics/article;
info:eu-repo/semantics/publishedVersion
Language:
English;
eng
Source:
Bulletin of Geography. Socio-economic Series; No. 58 (2022): December ; 141-154;
Bulletin of Geography. Socio-economic Series; Nr 58 (2022): December ; 141-154;
2083-8298;
1732-4254
Format:
application/pdf
Publisher:
Nicolaus Copernicus University in Toruń
Relation: https://apcz.umk.pl/BGSS/article/view/35666/34029
Subject:
convolutional neural network;
land cover;
building classification;
satellite imagery
Identifier: https://apcz.umk.pl/BGSS/article/view/35666
Data provider:
Akademicka Platforma Czasopism

Similar objects

Accuracy evaluation of convolutional neural network classification algorithms for building identification in rural and urban areas from very-high-resolution satellite imagery in Jambi, Indonesia

Creator:Nugroho, Daniel | Dimyati, Muhammad | Laswanto

Date:2022.12.09

Type:text

Land-Use Planning and Satellite Imagery Used for Green Areas Protection – Case Study of the City of Łódź, Poland

Creator:Feltynowski, Marcin

Date:2016.05.06 | 2015.12

Type:image

LAND-COVER MODELLING USING CORINE LAND COVER DATA AND MULTI-LAYER PERCEPTRON

Creator:Dzieszko, Piotr

Date:2014.03.27

Type:other

Changes of the ecosystem structure in rural areas on the example of the Łubowo commune (Wielkopolska region)

Creator:Pieczka, Daria | Stępniewska, Małgorzata

Date:2022.12.14

Type:text

ACCURACY OF THE SOIL SEALING ENHANCEMENT PRODUCT FOR POLAND

Date:2016.09.15

Type:other

Natural Capital Changes in Poland – Integrating Spatial and Economic Approach

Creator:TELEGA, Ivan | TELEGA, Agnieszka

Date:2020.11.25

Type:text

FRANZISCEAN CADASTRE IN LANDSCAPE STRUCTURE RESEARCH: A SYSTEMATIC REVIEW

Creator:Dolejš, Martin | Forejt, Michal

Date:2019.03.31

Type:other

TRANSFORMATION OF THE LANDSCAPE STRUCTURE OF THE SELECTED TESTING GROUNDS IN THE TRI-CITY AGGLOMERATION IN THE YEARS 1985–2012

Creator:Korwel-Lejkowska, Barbara

Date:2020.03.31

Type:other

Federacja Bibliotek Cyfrowych

Object's details: Accuracy evaluation of convolutional neural network classification algorithms for building identification in rural and urban areas from very-high-resolution satellite imagery in Jambi, Indonesia

Description

Similar objects